This seems like very standard ML. I’m not surprised it works, but also it likely takes a huge amount of training data (i.e. print samples) to recognize a specific machine.

I’ve done stuff like this. For instance I took a pre-trained model that could identify animals and used reinforcement learning to feed it thousands of annotated images of my cats. After this fine-tuning it could reliably tell the difference between them. Useful? Yes. Neat? Yes. But it’s not like it can identify a cat it’s never been trained on.

So it’s interesting and useful, but not as impressive or useful as the article makes it seem.

Also I’m sure something as simple as changing a nozzle or even what slicer is used would completely throw it off.

I really like this game. Agreed with the other comment about the endgame being a little weak but it’s still early in development and the content they’ve added has been great.

I love my merrel vapor gloves. Thanks for the recommendation.

Even an overripe banana is better than most things people might reach for instead. Don’t stress about banana ripeness - pass on the cookie and eat whatever banana you like.

Beautiful! Thanks for sharing.

Looks cozy! If you’ll forgive a bit of unsolicited advice: use tacks instead of tape where possible. Tacks leave behind a tiny hole that can easily be completely erased with a tiny bit of touch up paint whereas tape can pull off large sections of paint and really mess up the sheetrock when removed.

Love the laptop stickers!

Ironically AI would probably work ok here whereas excel is using a human-designed pattern matching heuristic that apparently either has a bug or didn’t take into account your locale properly. I say that as someone with a relatively negative opinion of ai

This is a task ai would do well at whereas most of the Excel workflow it would not.

It’s actually because January is also misspelled. Or possibly because Excel’s language/region isn’t set up right (I see your month abbreviations aren’t us-eng… If excel is in us-eng it likely isn’t going to identify them properly.

Many houseplants you buy from the hardware store or similar have been terribly mistreated by the store and transport process so they’ll show signs of stress within days of bringing them home usually.

New plant owners often assume they’re doing something wrong, but you have to remember the plant just went through some major trauma so it’s going to have issues for a little bit.

Just water and care for it as prescribed and it’ll usually get better eventually.

Bonus tip: buy a plant from a locally nursery and it’ll likely be healthy when you get it :)

This is something I’m struggling with a bit actually.

I created a custom peer to peer networking library for an old game from the 90s. It uses an ICE (webRTC) library with a signaling server to establish peer to peer connections. I looked into libp2p but I can’t wrap my head around how a DHT would be better than my simple signaling / lobby server. Yes, you’d have lots of potential relay servers around, but I already use a TURN server provoder for my current solution that has global relays for pennies per month. And Kademlia/DHT doesn’t remove the need for a primary server somewhere because every new client needs an initial peer to connect - so I have to provide a static peer anyway. Not sure how this is any different than a server.

Anyway - I really like libp2p and want to explore the option, but that’s my experience with an alternative p2p option.

All of his books are just wonderful.

If this was real they’d definitely say 0 fat, 0 sodium, 0 sugar. Companies are allowed to round down under a certain amount un the US

James Hoffman did a vid about this machine: https://youtu.be/qkfXNE3mkXA

Shirokuma Cafe (polar bear’s Cafe).

Paprika. To see the parade for the first time again… Wow.

Keio line is in Japan. So technically it’s a train-nigiri.

Wow one of her old ones. New site is https://darebee.com/ and a great resource!

Those look very nice as well, thank you! I’ll report back if I get a pair.

Thank you!

Thanks, I’ll take a look